1 / 26

Multi-model Estimation with J-linkage

Multi-model Estimation with J-linkage. Jeongkyun Lee. Motivation. How do we find parameters of a model that contains outliers? Application in vision: geometric figure fitting, planar surface detection, motion segmentation, etc. Single-model Estimation. Least Squares

khuong
Download Presentation

Multi-model Estimation with J-linkage

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Multi-model Estimation with J-linkage Jeongkyun Lee

  2. Motivation How do we find parameters of a model that contains outliers? • Application in vision: geometric figure fitting, planar surface detection, motion segmentation, etc.

  3. Single-model Estimation • Least Squares • Least Median of Squares (LMedS) • Random Sample Consensus (RANSAC) • M-SAC • MLESAC • PROSAC • Etc.

  4. Least Squares • Calculate parameters of model function • Overdetermined data set • Minimized sum of squared residuals with a matrix form,

  5. Least Squares Without outliers With outliers

  6. RANSAC • Iterative method • Non-deterministic • Robust fitting in the presence of outliers • Simple algorithm Algorithm • M. A. Fischler, R. C. Bolles. Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography. Comm. of the ACM, Vol 24, pp 381-395, 1981.

  7. RANSAC

  8. Multi-model Estimation • Residual histogram analysis (RHA) • Sequential RANSAC • Multi-RANSAC • J-linkage • Kernel fitting (KF) • Mean-shift (MS) • Etc.

  9. Multi-model Estimation with J-Linkage • Fit multiple structures simultaneously • Require no initial parameters: # of models, model parameters Algorithm Given N points, Generate M model hypothesis (Random sampling) Build a N x M matrix, comprised of Preference Sets of points J-linkage clustering

  10. Multi-model Estimation with J-Linkage Preference Set

  11. Multi-model Estimation with J-Linkage • Random Sampling • A minimal sample set (MSS) is constructed in a way that neighbouring points are selected with higher probability. • One sample is selected with uniform probability • If a point is given, then has the following probability: Z is a normalized constant, is chosen heuristically.

  12. Multi-model Estimation with J-Linkage • J-linkage Clustering • Starting from all singletons • Each sweep of the algorithm merges the two clusters with the smallest distance Measure the degree of overlap of the two sets and ranges from 0 (identical sets) to 1 (disjoint sets)

  13. Multi-model Estimation with J-Linkage • J-linkage Clustering Assumption One-to-one matching between a point and a model Algorithm

  14. Multi-model Estimation with J-Linkage • Example 1 2 3 4

  15. Multi-model Estimation with J-Linkage • Results

  16. Multi-model Estimation with J-Linkage • Results

  17. Multi-model Estimation with J-Linkage • Results

  18. Multi-model Estimation with J-Linkage • Results

  19. Multi-model Estimation with J-Linkage • Other Results 1 David F. Fouhey, “Multi-model Estimation in the Presence of Outliers”

  20. Multi-model Estimation with J-Linkage • Other Results 1 David F. Fouhey, “Multi-model Estimation in the Presence of Outliers”

  21. Multi-model Estimation with J-Linkage • Other Results 2 HanziWang, “Robust Multi-Structure Fitting”, A tutorial in ACCV 2012.

  22. Multi-model Estimation with J-Linkage • Other Results 2 HanziWang, “Robust Multi-Structure Fitting”, A tutorial in ACCV 2012.

  23. Reference • David F. Fouhey, “Multi-model Estimation in the Presence of Outliers” • Stefano Branco, “RANSAC/MLESAC, Estimating parameters of models with outliers” • Hanzi Wang, “Robust Multi-Structure Fitting”, A tutorial in ACCV 2012.

  24. Thank you!

  25. Appendix

  26. Appendix

More Related